DOCSLIB.ORG

Fuzzing Semantic Misinterpretation for Voice Assistant Applications

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Fuzzing Semantic Misinterpretation for Voice Assistant Applications Life after Speech Recognition: Fuzzing Semantic Misinterpretation for Voice Assistant Applications Yangyong Zhang, Lei Xu, Abner Mendoza, Guangliang Yang, Phakpoom Chinprutthiwong, Guofei Gu SUCCESS Lab, Dept. of Computer Science & Engineering Texas A&M University fyangyong, xray2012, abmendoza, ygl, [email protected], [email protected] Abstract—Popular Voice Assistant (VA) services such I. INTRODUCTION as Amazon Alexa and Google Assistant are now rapidly appifying their platforms to allow more flexible and The Voice User Interface (VUI) is becoming a diverse voice-controlled service experience. However, the ubiquitous human-computer interaction mechanism to ubiquitous deployment of VA devices and the increasing enhance services that have limited or undesired physical number of third-party applications have raised security interaction capabilities. VUI-based systems, such as and privacy concerns. While previous works such as Voice Assistants (VA), allow users to directly use voice hidden voice attacks mostly examine the problems of inputs to control computational devices (e.g., tablets, VA services’ default Automatic Speech Recognition (ASR) smart phones, or IoT devices) in different situations. component, our work analyzes and evaluates the security With the fast growth of VUI-based technologies, a large of the succeeding component after ASR, i.e., Natural Language Understanding (NLU), which performs semantic number of applications designed for Voice Assistant interpretation (i.e., text-to-intent) after ASR’s acoustic- (VA) services (e.g., Amazon Alexa Skills and Google to-text processing. In particular, we focus on NLU’s Assistant Actions) are now available. Amazon Alexa Intent Classifier which is used in customizing machine currently has more than 30,000 applications, or vApps1. understanding for third-party VA Applications (or vApps). We find that the semantic inconsistency caused by the Several attacks have been reported to affect the in- improper semantic interpretation of an Intent Classifier tegrity of existing Automatic Speech Recognition (ASR) can create the opportunity of breaching the integrity of component in vApp processing. For example, acoustic- vApp processing when attackers delicately leverage some based attacks [19], [36], [33], [35], [23] leverage sounds common spoken errors. that are unrecognizable or inaudible by the human. More recently, Kumar et al. [28] presented an empirical study of vApp squatting attacks based on speech misinterpre- tation (for example, an Alexa Skill named “Test Your In this paper, we design the first linguistic-model- Luck” could be routed to a maliciously uploaded skill guided fuzzing tool, named LipFuzzer, to assess the with a confusing name of “Test Your Lock”). This attack security of Intent Classifier and systematically discover works, with proof-of-concept, in a remote manner that potential misinterpretation-prone spoken errors based on could potentially be more powerful than acoustic-based vApps’ voice command templates. To guide the fuzzing, we construct adversarial linguistic models with the help of attacks. Statistical Relational Learning (SRL) and emerging Natu- Despite recent evidence [28] of launching potential ral Language Processing (NLP) techniques. In evaluation, vApp squatting attacks, little effort has been made to un- we have successfully verified the effectiveness and accuracy of LipFuzzer. We also use LipFuzzer to evaluate both cover the root cause of speech misinterpretation in vApp Amazon Alexa and Google Assistant vApp platforms. We processing. In this paper, we devise a first representative have identified that a large portion of real-world vApps Voice Assistant (VA) Architecture, as shown in Figure 1, are vulnerable based on our fuzzing result. from which we study the core components involved in proper speech interpretation. After closely scrutinizing the VA architecture, we found that both the Automatic Speech Recognition (ASR) and the Natural Language Network and Distributed Systems Security (NDSS) Symposium 2019 24-27 February 2019, San Diego, CA, USA Understanding (NLU) components play a central role in ISBN 1-891562-55-X https://dx.doi.org/10.14722/ndss.2019.23525 1vApp is the generalized name used in this paper for Amazon Alexa www.ndss-symposium.org Skills, Google Assistant Actions. proper speech recognition and interpretation. Previous Natural Intent Automatic Textual Language Classifier works have only studied the ASR text interpretation Audio Speech Data Understanding Input Recognition (NLU) component. In the NLU, an Intent Classifier uses voice (ASR) command templates (or templates) to match intents Intents Audio Response Output (similar to Intent Message in Android) with textual data Engine Textual vAppThird Response InstancesParty obtained after ASR’s text interpretation. Then, intents Speech Processing Gadgets are used to reach vApps with specific functionality. From the vApp security perspective, the Intent Classifier Fig. 1: VUI-based VA Architecture. plays a more important role when interpreting users’ voice commands. The reason is that the Intent Classifier is the last step of the interpretation process. It has commands. For example, a user could be simply using the capability of not only determining users’ semantic regional vocabulary (i.e. words or expressions that are intents, but also fixing the ASR’s potential transcription used in a dialect area but not commonly recognizable errors. Second, while ASR is a default built-in service in other areas) rather than pronunciation issue alone. component, the construction of the Intent Classifier’s Moreover, it is unpredictable when and how a user semantic classification is contributed by both vApp would speak differently. All of these factors make the developers and service providers. Particularly, third- voice command fuzzing difficult because of the large party developers can upload voice command templates searching space. to modify the unified intent classification tree used by all users (more details are illustrated in Section II). To overcome the aforementioned design challenges, As a result, it creates the opportunity for misbehaving we propose a novel linguistic-model-guided fuzzing developers to maliciously modify the intent matching tool, called LipFuzzer. Our tool generates potential process of the NLU. voice commands that are likely to incur a seman- tic inconsistency such that a user reaches an unin- However, it is challenging to systematically study tended vApp/functionality (i.e. users think they use how NLU’s Intent Classifier is penetrated to incur voice commands correctly but yield unwanted results). semantic inconsistency between users’ intents and VA’s For convenience, we name any voice commands that machine understanding. First, mainstream VA plat- can lead to such inconsistency as LAPSUS.3 LipFuzzer forms, such as Amazon Alexa, Google Assistant, and addresses the two aforementioned challenges in two almost all vApps are in closed development. Thus, components. First, to decide mutation fields, we realize it is difficult to conduct a white box analysis. Also, that the state-of-the-art Natural Language Processing due to the strong privacy enforcement, it is impossible (NLP) techniques can be used to extract computational to get real users’ speech input and the corresponding linguistic data. Thus, we design LipFuzzer’s basic tem- vApp response output. Thus, conducting large-scale, plate fuzzing by first mutating NLP pre-processed voice real-world data-driven analysis is also very challenging. command templates. Then, we input mutated voice Our Approach. In this work, we assess speech mis- commands to VA devices by using machine speech interpretation through the black-box mutation fuzzing synthesis to eliminate the human factor of producing of voice command templates, which are used as inputs ASR-related misinterpretation. Second, to reduce the of Intent Classifier for matching intents. Our goal is search space of the basic fuzzing, in the linguistic mod- to systematically evaluate how Intent Classifier behaves eling component, we train adversarial linguistic models when inputting different forms of voice commands. named LAPSUS Models by adopting Bayesian Networks However, it is not straight-forward to design such a (BNs). BNs are constructed statistically with linguistic fuzzing scheme. First, the computability of vApp I/O knowledge related to LAPSUS. The template fuzzing is is very limited as both input and output of vApps are then guided with linguistic model query results. As a in the speech form, i.e., you can only speak with a VA result, LipFuzzer is able to perform effective mutation- device or listen to the audio response2. Thus, we have based fuzzing on seed template inputs (gathered from to determine mutation fields that we can work on in the existing vApp user guidance available online). context of vApp processing. Moreover, it is important In our evaluation, we first showcase that Intent Clas- to eliminate the effect of ASR’s text interpretation so sifier is indeed the root cause of the misinterpretation. that error propagation is minimized. Second, in [28], Then, we show that LipFuzzer can systematically pin- the authors suggest that vApp squatting attacks are point semantic inconsistencies with the help of linguistic caused by pronunciation-based interpretation errors of models generated from existing linguistic knowledge. ASR. However, in reality, ambiguous natural languages incur many more different forms of confusing voice Furthermore, we scan Alexa Skill Store and Google
Load more

Recommended publications
  • Voice Interfaces
    VIEW POINT VOICE INTERFACES Abstract A voice-user interface (VUI) makes human interaction with computers possible through a voice/speech platform in order to initiate an automated service or process. This Point of View explores the reasons behind the rise of voice interface, key challenges enterprises face in voice interface adoption and the solution to these. Are We Ready for Voice Interfaces? Let’s get talking! IO showed the new promise of voice offering integrations with their Voice interfaces. Assistants. Since Apple integration with Siri, voice interfaces has significantly Almost all the big players (Google, Apple, As per industry forecasts, over the next progressed. Echo and Google Home Microsoft) have ‘office productivity’ decade, 8 out of every 10 people in the have demonstrated that we do not need applications that are being adopted by world will own a device (a smartphone or a user interface to talk to computers businesses (Microsoft and their Office some kind of assistant) which will support and have opened-up a new channel for Suite already have a big advantage here, voice based conversations in native communication. Recent demos of voice but things like Google Docs and Keynote language. Just imagine the impact! based personal assistance at Google are sneaking in), they have also started Voice Assistant Market USD~7.8 Billion CAGR ~39% Market Size (USD Billion) 2016 2017 2018 2019 2020 2021 2022 2023 The Sudden Interest in Voice Interfaces Although voice technology/assistants Voice Recognition Accuracy Convenience – speaking vs typing have been around in some shape or form Voice Recognition accuracy continues to Humans can speak 150 words per minute for many years, the relentless growth of improve as we now have the capability to vs the typing speed of 40 words per low-cost computational power—and train the models using neural networks minute.
    [Show full text]
  • NLP-5X Product Brief
    NLP-5x Natural Language Processor With Motor, Sensor and Display Control The NLP-5x is Sensory’s new Natural Language Processor targeting consumer electronics. The NLP-5x is designed to offer advanced speech recognition, text-to-speech (TTS), high quality music and speech synthesis and robotic control to cost-sensitive high volume products. Based on a 16-bit DSP, the NLP-5x integrates digital and analog processing blocks and a wide variety of communication interfaces into a single chip solution minimizing the need for external components. The NLP-5x operates in tandem with FluentChip™ firmware - an ultra- compact suite of technologies that enables products with up to 750 seconds of compressed speech, natural language interface grammars, TTS synthesis, Truly Hands-Free™ triggers, multiple speaker dependent and independent vocabularies, high quality stereo music, speaker verification (voice password), robotics firmware and all application code built into the NLP-5x as a single chip solution. The NLP-5x also represents unprecedented flexibility in application hardware designs. Thanks to the highly integrated architecture, the most cost-effective voice user interface (VUI) designs can be built with as few additional parts as a clock crystal, speaker, microphone, and few resistors and capacitors. The same integration provides all the necessary control functions on-chip to enable cost-effective man-machine interfaces (MMI) with sensing technologies, and complex robotic products with motors, displays and interactive intelligence. Features BROAD
    [Show full text]
  • A Guide to Chatbot Terminology
    Machine Language A GUIDE TO CHATBOT TERMINOLOGY Decision Trees The most basic chatbots are based on tree-structured flowcharts. Their responses follow IF/THEN scripts that are linked to keywords and buttons. Natural Language Processing (NLP) A computer’s ability to detect human speech, recognize patterns in conversation, and turn text into speech. Natural Language Understanding A computer’s ability to determine intent, especially when what is said doesn’t quite match what is meant. This task is much more dicult for computers than Natural Language Processing. Layered Communication Human communication is complex. Consider the intricacies of: • Misused phrases • Intonation • Double meanings • Passive aggression • Poor pronunciation • Regional dialects • Subtle humor • Speech impairments • Non-native speakers • Slang • Syntax Messenger Chatbots Messenger chatbots reside within the messaging applications of larger digital platforms (e.g., Facebook, WhatsApp, Twitter, etc.) and allow businesses to interact with customers on the channels where they spend the most time. Chatbot Design Programs There’s no reason to design a messenger bot from scratch. Chatbot design programs help designers make bots that: • Can be used on multiple channels • (social, web, apps) • Have custom design elements • (response time, contact buttons, • images, audio, etc.) • Collect payments • Track analytics (open rates, user • retention, subscribe/unsubscribe • rates) • Allow for human takeover when • the bot’s capabilities are • surpassed • Integrate with popular digital • platforms (Shopify, Zapier, Google • Site Search, etc.) • Provide customer support when • issues arise Voice User Interface A voice user interface (VUI) allows people to interact with a computer through spoken commands and questions. Conversational User Interface Like a voice user interface, a conversational user interface (CUI) allows people to control a computer with speech, but CUI’s dier in that they emulate the nuances of human conversation.
    [Show full text]
  • Voice User Interface on the Web Human Computer Interaction Fulvio Corno, Luigi De Russis Academic Year 2019/2020 How to Create a VUI on the Web?
    Voice User Interface On The Web Human Computer Interaction Fulvio Corno, Luigi De Russis Academic Year 2019/2020 How to create a VUI on the Web? § Three (main) steps, typically: o Speech Recognition o Text manipulation (e.g., Natural Language Processing) o Speech Synthesis § We are going to start from a simple application to reach a quite complex scenario o by using HTML5, JS, and PHP § Reminder: we are interested in creating an interactive prototype, at the end 2 Human Computer Interaction Weather Web App A VUI for "chatting" about the weather Base implementation at https://github.com/polito-hci-2019/vui-example 3 Human Computer Interaction Speech Recognition and Synthesis § Web Speech API o currently a draft, experimental, unofficial HTML5 API (!) o https://wicg.github.io/speech-api/ § Covers both speech recognition and synthesis o different degrees of support by browsers 4 Human Computer Interaction Web Speech API: Speech Recognition § Accessed via the SpeechRecognition interface o provides the ability to recogniZe voice from an audio input o normally via the device's default speech recognition service § Generally, the interface's constructor is used to create a new SpeechRecognition object § The SpeechGrammar interface can be used to represent a particular set of grammar that your app should recogniZe o Grammar is defined using JSpeech Grammar Format (JSGF) 5 Human Computer Interaction Speech Recognition: A Minimal Example const recognition = new window.SpeechRecognition(); recognition.onresult = (event) => { const speechToText = event.results[0][0].transcript;
    [Show full text]
  • Eindversie-Paper-Rianne-Nieland-2057069
    Talking to Linked Data: Comparing voice interfaces for general­purpose data Master thesis of Information Sciences Rianne Nieland Vrije Universiteit Amsterdam [email protected] ABSTRACT ternet access (Miniwatts Marketing Group, 2012) and People in developing countries cannot access informa- 31.1% is literate (UNESCO, 2010). tion on the Web, because they have no Internet access and are often low literate. A solution could be to pro- A solution to the literacy and Internet access problem vide voice-based access to data on the Web by using the is to provide voice-based access to the Internet by us- GSM network. Related work states that Linked Data ing the GSM network (De Boer et al., 2013). 2G mobile could be a useful input source for such voice interfaces. phones are digital mobile phones that use the GSM net- work (Fendelman, 2014). In Africa the primary mode The aim of this paper is to find an efficient way to make of telecommunication is mobile telephony (UNCTAD, general-purpose data, like Wikipedia information, avail- 2007). able using voice interfaces for GSM. To achieve this, we developed two voice interfaces, one for Wikipedia This paper is about how information on the Web ef- and one for DBpedia, by doing requirements elicitation ficiently can be made available using voice interfaces from literature and developing a voice user interface and for GSM. We developed two voice interfaces, one us- conversion algorithms for Wikipedia and DBpedia con- ing Wikipedia and the other using DBpedia. In this cepts. With user tests the users evaluated the two voice paper we see Wikipedia and DBpedia as two different interfaces, to be able to compare them.
    [Show full text]
  • Voice Assistants and Smart Speakers in Everyday Life and in Education
    Informatics in Education, 2020, Vol. 19, No. 3, 473–490 473 © 2020 Vilnius University, ETH Zürich DOI: 10.15388/infedu.2020.21 Voice Assistants and Smart Speakers in Everyday Life and in Education George TERZOPOULOS, Maya SATRATZEMI Department of Applied Informatics, University of Macedonia, Thessaloniki, Greece Email: [email protected], [email protected] Received: November 2019 Abstract. In recent years, Artificial Intelligence (AI) has shown significant progress and its -po tential is growing. An application area of AI is Natural Language Processing (NLP). Voice as- sistants incorporate AI by using cloud computing and can communicate with the users in natural language. Voice assistants are easy to use and thus there are millions of devices that incorporates them in households nowadays. Most common devices with voice assistants are smart speakers and they have just started to be used in schools and universities. The purpose of this paper is to study how voice assistants and smart speakers are used in everyday life and whether there is potential in order for them to be used for educational purposes. Keywords: artificial intelligence, smart speakers, voice assistants, education. 1. Introduction Emerging technologies like virtual reality, augmented reality and voice interaction are reshaping the way people engage with the world and transforming digital experiences. Voice control is the next evolution of human-machine interaction, thanks to advances in cloud computing, Artificial Intelligence (AI) and the Internet of Things (IoT). In the last years, the heavy use of smartphones led to the appearance of voice assistants such as Apple’s Siri, Google’s Assistant, Microsoft’s Cortana and Amazon’s Alexa.
    [Show full text]
  • Integrating a Voice User Interface Into a Virtual Therapy Platform Yun Liu Lu Wang William R
    Integrating a Voice User Interface into a Virtual Therapy Platform Yun Liu Lu Wang William R. Kearns University of Washington, Seattle, University of Washington, Seattle, University of Washington, Seattle, WA 98195, USA WA 98195, USA WA 98195, USA [email protected] [email protected] [email protected] Linda E Wagner John Raiti Yuntao Wang University of Washington, Seattle, University of Washington, Seattle, Tsinghua University, Beijing 100084, WA 98195, USA WA 98195, USA China & University of Washington, [email protected] [email protected] WA 98195, USA [email protected] Weichao Yuwen University of Washington, Tacoma, WA 98402, USA [email protected] ABSTRACT ACM Reference Format: More than 1 in 5 adults in the U.S. serving as family caregivers are Yun Liu, Lu Wang, William R. Kearns, Linda E Wagner, John Raiti, Yuntao Wang, and Weichao Yuwen. 2021. Integrating a Voice User Interface into a the backbones of the healthcare system. Caregiving activities sig- Virtual Therapy Platform. In CHI Conference on Human Factors in Computing nifcantly afect their physical and mental health, sleep, work, and Systems Extended Abstracts (CHI ’21 Extended Abstracts), May 08–13, 2021, family relationships over extended periods. Many caregivers tend Yokohama, Japan. ACM, New York, NY, USA, 6 pages. https://doi.org/10. to downplay their own health needs and have difculty accessing 1145/3411763.3451595 support. Failure to maintain their own health leads to diminished ability in providing high-quality care to their loved ones. Voice user interfaces (VUIs) hold promise in providing tailored support 1 INTRODUCTION family caregivers need in maintaining their own health, such as Chronic diseases, such as diabetes and cancer, are the leading causes fexible access and handsfree interactions.
    [Show full text]
  • Master Thesis
    Czech Technical University in Prague Faculty of Electrical Engineering Department of Computer Science MASTER THESIS Creation of Dialog Applications Based on Schema.org Ontology Bc. Tatiana Okonechnikova Supervisor: Ing. Jan Sediv´y,CSc.ˇ January 2019 Author Statement I declare that the presented work was developed independently and that I have listed all sources of information used within it in accordance with the methodical in- structions for observing the ethical principles in the preparation of university theses. Prague, 1st January 2019 ::::::::::::::::::::: signature 3 ZADÁNÍ DIPLOMOVÉ PRÁCE I. OSOBNÍ A STUDIJNÍ ÚDAJE Příjmení: Okonechnikova Jméno: Tatiana Osobní číslo: 393194 Fakulta/ústav: Fakulta elektrotechnická Zadávající katedra/ústav: Katedra počítačů Studijní program: Otevřená informatika Studijní obor: Datové vědy II. ÚDAJE K DIPLOMOVÉ PRÁCI Název diplomové práce: Tvorba dialogových aplikací na základě ontologie schema.org Název diplomové práce anglicky: Creation of dialog applications based on schema.org ontology Pokyny pro vypracování: Review the conversational AI technologies technologies. Focus on a semi-automatic creation of a dialog from structured and semi-structured data. As a source of structured data use the RDF knowledge database (DBpedia, Wikidata). Use a straightforward static web page as a representant of the semi-structured data. Design and implement semi-automatic application creating a simple dialog for intelligent speakers, such as Amazon Alexa or Google Home. Select a topic, (for example movies) find the RDF database or a web portal and build and test simple dialogs conveying user selected information. Test the application with at least three users and report the results. Seznam doporučené literatury: Speech and Language Processing https://web.stanford.edu/~jurafsky/slp3/ (vybrané kapitoly) Jméno a pracoviště vedoucí(ho) diplomové práce: Ing.
    [Show full text]
  • Context-Aware Intelligent User Interfaces for Supporting Sytem
    Context-Aware Intelligent User Interfaces for Supporting System Use Vom Fachbereich Informatik der Technischen Universität Darmstadt genehmigte Dissertation zur Erlangung des akademischen Grades Dr.-Ing. von Dipl.-Inform. Melanie Hartmann geboren in Seeheim-Jugenheim Referenten: Prof. Dr. Max Mühlhäuser (TU Darmstadt) Prof. Dr. Rainer Malaka (Universität Bremen) Tag der Einreichung: 4. Dezember 2009 Tag der mündlichen Prüfung: 18. Januar 2010 Darmstadt 2010 Hochschulkennziffer D17 i Ehrenwörtliche Erklärung1 Hiermit erkläre ich, die vorgelegte Arbeit zur Erlangung des akademischen Grades “Dr.-Ing.” mit dem Titel “Context-Aware Intelligent User Interfaces for Support- ing System Use” selbständig und ausschließlich unter Verwendung der angegebenen Hilfsmittel erstellt zu haben. Ich habe bisher noch keinen Promotionsversuch unter- nommen. Darmstadt, den 4. Dezember 2009 Melanie Hartmann 1Gemäß §9 Abs. 1 der Promotionsordnung der TU Darmstadt Abstract Two trends can be observed in current applications: the amount of functionality of- fered is constantly increasing and applications are more often used in mobile settings. Both trends often lead to a decrease in the usability of applications. This effect can be countered by Intelligent User Interfaces that facilitate the interaction between user and application. In order to support the user in an optimal way, the Intelligent User Interface has to be aware of the user’s needs and adapt the provided support to her current situation, i.e. her current context. The relevant context information can thereby be gathered from the environment (e.g. her current location) or from sophisticated user models that reflect the user’s behavior. In this thesis, we present a novel approach of combining user and environmental context information for supporting the system use.
    [Show full text]
  • Arxiv:2011.11315V1 [Eess.AS] 23 Nov 2020 in Public Areas Due to Its Risk of Privacy Leakage
    END-TO-END SILENT SPEECH RECOGNITION WITH ACOUSTIC SENSING Jian Luo, Jianzong Wang*, Ning Cheng, Guilin Jiang, Jing Xiao Ping An Technology (Shenzhen) Co., Ltd. ABSTRACT Silent speech interfaces (SSI) has been an exciting area of recent interest. In this paper, we present a non-invasive silent speech interface that uses inaudible acoustic signals to capture Acos(2휋푓푡) people’s lip movements when they speak. We exploit the speaker and microphone of the smartphone to emit signals and cos(2휋푓푡) listen to their reflections, respectively. The extracted phase LPF I features of these reflections are fed into the deep learning networks to recognize speech. And we also propose an end- LPF Q to-end recognition framework, which combines the CNN and sin(2휋푓푡) Coherent detector attention-based encoder-decoder network. Evaluation results on a limited vocabulary (54 sentences) yield word error rates of 8.4% in speaker-independent and environment-independent Fig. 1. Sensing lip movements with acoustic signals generated settings, and 8.1% for unseen sentence testing. by smart devices. Index Terms— silent speech interfaces, inaudible acoustic signals, attention-based encoder-decoder skin-attached sensors are very invasive to users. Besides, the reattachment of the sensors may cause changes in the recorded 1. INTRODUCTION signal, which will significantly degrade their performance [5]. Instead of the aforementioned approaches, another trend With the rapid development of speech recognition and natu- of works utilizes ultrasound. The use of high-frequency ul- ral language processing, voice user interface (VUI) has be- trasound (MHz level) has a long history in medical voice come a fundamental use case for today’s smart devices (e.g., interface research [9], aiming to provide an alternative to elec- smartphone, smartwatch, laptop, smart speaker, and smart trolarynx for some patients who have lost their voicebox.
    [Show full text]
  • A ROOM with a VUI – VOICE USER INTERFACES in the TESOL CLASSROOM by David Kent Woosong University Daejon, Republic of Korea Dbkent @ Wsu.Ac.Kr
    Teachng Englsh wth Technology, 20(3), 96-124, http://www.tewtjournal.org 96 A ROOM WITH A VUI – VOICE USER INTERFACES IN THE TESOL CLASSROOM by David Kent Woosong University Daejon, Republic of Korea dbkent @ wsu.ac.kr Abstract Disruptive technologies have seen how students interact with their teachers, how we as teachers now prepare and provide learning, and how we might best incorporate artificial intelligence into the classroom. To this end, the pedagogical affordances offered by the voice-user interface of digital assistants is explored. Instructional strategies supported by examples are then provided, along with means for actioning their use in the classroom and evaluating their appropriateness and viability for enhancing language learning. Keywords: digital assistants; voice-user interface; interaction; speaking 1. Introduction As instructors, we no longer talk about technology replacing teachers, or even teachers who use technology replacing those that do not (John & Wheeler, 2015); instead we expect to be incorporating technologies for learning into our classrooms. This means that as instructors today, we need to be able to competently apply that technology and competently assess and evaluate the suitability and appropriateness of how that technology has met intended teaching and learning objectives, while also understanding all levels of the educational potential behind its use, and assisting learners in being able to identify those elements as well (Fotos & Brown, 2004; Levy and Stockwell, 2006). This is important because teaching in the time of digital language learning sees us not just doing old things in new ways, but it has ushered in a total era of ‘newness.’ There are new things to do, new ways to think, new methods of managing relationships with others (and AI – artificial intelligence), and new practices in teaching that require us to adopt new skills and new abilities (Jones & Hafner, 2012).
    [Show full text]
  • Implementation of Voice User Interface Using Speech Recognition
    International Journal of Computer Applications (0975 – 8887) Volume 124 – No.10, August 2015 Implementation of Voice User Interface using Speech Recognition Pranali Joshi Ravi Patki Department of Computer Engineering Department of Computer Engineering Dr.D.Y.Patil College Of Engineering, Dr.D.Y.Patil College of Engineering, Ambi, Pune Ambi, Pune ABSTRACT these two gives a faster way of giving input to the computer A voice–user interface (VUI) makes human interaction with and get output equally faster. The latest trend is of using touch computers possible through a voice/speech platform in order sensitive screens to provide input to the computer, but it has to initiate an automated service or process. A VUI is the its own disadvantages. The proposed system will provide the interface to any speech application. Controlling a machine by ultimate 3rd input pattern parallel to mouse and keyboard. simply talking to it was science fiction only a short time ago. This will give a completely new dimension to the computer Until recently, this area was considered to be artificial user interface. It will provide faster means to give multiple intelligence. However, with advances in technology, VUIs inputs at the same time. have become more commonplace, and people are taking Ubiquitous computing (ubicomp) refers to a new generation advantage of the value that these hands-free, eyes-free of computing in which the computer completely permeates the interfaces provide in many situations. life of the user. In ubiquitous computing, computers become a The system will be implemented by using techniques such as helpful but invisible force, assisting the user in meeting his or speech and language processing, human language technology, her needs without getting in the way.
    [Show full text]